pyvene-interventions

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the pyvene package via pip and downloads models or interventions from HuggingFace Hub (e.g., meta-llama/Llama-2-7b-hf, zhengxuanzenwu/intervenable_honest_llama2_chat_7B). These are standard operations for the library using well-known services.
  • [COMMAND_EXECUTION]: Provides standard installation instructions (pip install pyvene) and standard Python code for performing neural network interventions, training, and saving results.
  • [INDIRECT_PROMPT_INJECTION]: Involves processing user-supplied prompts for model interpretability tasks. The skill follows research methodologies with clear ingestion points (text prompts), boundary markers (string delimiters), and relies on standard transformers tokenization for input handling. Capabilities are limited to model analysis and saving intervention states.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 03:22 PM